Head to head
Esc

Models · slot A

to navigate to pick

FLUX.1 Kontext [dev] Black Forest Labs FLUX.2 [klein] 4B Black Forest Labs

Settled by community votes across 17 shared challenges, with an AI judge weighing in on each.

FLUX.1 Kontext [dev]

16.5 arena score

#58 of 62 in Text-to-Image

Skill signature · Text-to-Image

FLUX.2 [klein] 4B

22.3 arena score

#32 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.1 Kontext [dev]

0%

win rate

Ties

0%

FLUX.2 [klein] 4B

0%

win rate

Shared challenges 17

Challenge by challenge

The strongest take from each model on every shared challenge, with the AI judge's read.

Geometric Composition

Text-to-Image

“A glass cube on a wooden table. Inside the cube is a small blue sphere. On top of the cube sits a red book. A green plant is behind the cube, partially visible through the glass. Soft window light from the left.”

FLUX.1 Kontext [dev]
FLUX.2 [klein] 4B

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Excellent representation of materials with realistic light reflections on the blue sphere.
  • + The plant is clearly visible through the glass cube as requested.
  • + High visual fidelity in textures, especially the wood grain and paper edges.
  • The book is slightly too large for the cube's top surface, creating a less balanced composition.

FLUX.2 [klein] 4B

  • + Perfect spatial logic with the book dimensions matching the top of the cube exactly.
  • + Subtle, realistic lighting that accurately captures the 'soft window light' from the left.
  • + Clean and minimalist composition that feels very intentional.
  • The plant in the background is less visible through the glass compared to Model A.
  • The sphere has less detailed specular highlights.

Verdict: Both models followed the prompt instructions perfectly, including the specific spatial arrangements and lighting. FLUX.1 Kontext [dev] produced a more vibrant image with better material physics, specifically the way the plant refracts and appears through the glass, while FLUX.2 [klein] 4B offered a more balanced composition with a better-scaled book.

Candid Street Photography

Text-to-Image

“A candid street photo of an elderly Japanese man repairing a red bicycle in light rain, reflections on wet pavement, shallow depth of field, 50mm lens, natural skin texture, imperfect framing, motion blur from passing cars, cinematic but realistic, no stylization.”

FLUX.1 Kontext [dev]
FLUX.2 [klein] 4B

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Excellent character likeness and facial detail
  • + Vibrant colors on the red bicycle
  • + Clean composition with good street depth
  • The subject is posing with the bike rather than repairing it
  • Background cars are static and lack the requested motion blur
  • Rain effect looks like a simple overlay filter

FLUX.2 [klein] 4B

  • + Stronger adherence to the 'repairing' action in the prompt
  • + More realistic skin texture and candid lighting
  • + Better integration of the rain effect and wet pavement reflections
  • Structural issues with the bicycle frame near the pedals
  • The subject's hands are slightly muddy in detail
  • The background cars are too sharp for the requested motion blur

Verdict: Both models failed to accurately capture motion blur from passing cars, but FLUX.2 [klein] 4B followed the 'repairing' prompt much better than FLUX.1 Kontext [dev], which showed a man simply sitting on a bike. Although FLUX.1 Kontext [dev] had better facial clarity, FLUX.2 [klein] 4B felt more like a candid street photo with more natural color grading and environment interaction.

Fantasy Warrior

Text-to-Image

“Close portrait of a battle-worn paladin in ornate engraved plate armor, hair braided with small beads, faint scars and dirt on the skin, warm torchlight reflecting off metal, shallow depth of field, bokeh sparks, lifelike eyes, highly detailed texture on leather straps and cloth underlayer.”

FLUX.1 Kontext [dev]
FLUX.2 [klein] 4B

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Atmospheric use of warm torchlight and high-contrast shadows
  • + Exquisite detail on the engraved plate armor
  • + Strong cinematic composition and depth of field
  • Failed to include the specific prompt instruction for braided hair with beads
  • The leather straps are less visible compared to the other model

FLUX.2 [klein] 4B

  • + Excellent adherence to the 'braided hair with small beads' instruction
  • + Visible leather straps and cloth underlayer textures as requested
  • + Includes visible torches that explain the lighting source
  • The lighting is a bit flat compared to Model A's dramatic atmosphere
  • The skin texture lacks some of the 'dirt' and grittiness requested, appearing a bit clean despite the scars

Verdict: FLUX.2 [klein] 4B followed the prompt more accurately, specifically including the braided hair and beads which FLUX.1 Kontext [dev] missed. However, FLUX.1 Kontext [dev] produced a more cinematically appealing image with superior lighting and more intricate armor engraving.

Modern Clean Menu

Text-to-Image

“Modern minimalist restaurant menu design, white background with colorful food photos in grid, sections for appetizers/pizza/mains, bold sans-serif fonts, vibrant accents, clean professional layout for casual dining.”

FLUX.1 Kontext [dev]
FLUX.2 [klein] 4B

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Excellent typography rendering with clean, bold sans-serif fonts.
  • + Strong adherence to the grid layout request.
  • + High-quality, realistic food photography that looks professional.
  • Text content is nonsensical gibberish.
  • The layout is a bit repetitive with the 'Lgannfog' text blocks.

FLUX.2 [klein] 4B

  • + Successfully includes pricing columns which feels more like a real menu.
  • + Good variety of food shapes and vibrant colors.
  • + Captures the 'casual dining' vibe well with a structured header and logo area.
  • The bold fonts are slightly stylized/rounded, missing the requested 'clean bold sans-serif' look.
  • The image grid has inconsistent spacing and some overlapping issues.
  • Text is highly garbled and unreadable even for a mock-up.

Verdict: FLUX.1 Kontext [dev] produces a much cleaner and more professional design that closely follows the minimalist aesthetic and grid layout. While FLUX.2 [klein] 4B attempts a more complex menu structure with pricing, the overall visual quality and typographic execution of FLUX.1 Kontext [dev] are superior for graphic design tasks.

Magic Burger Explosion: Fiery Photorealism Challenge

Text-to-Image

“Ad for 'Magic Burger'. Dynamic, exploded burger with all components (bun, patty, cheese, lettuce, tomato, sauce) suspended in mid-air. Emphasize photorealistic detail and a sense of motion. Dark, fiery background with glowing embers. Integrate text: 'MAGIC BURGER' as a prominent title, 'LIMITED TIME ONLY' as a secondary message, and '€6.99' in a starburst, all rendered with a fiery, glowing effect.”

FLUX.1 Kontext [dev]
FLUX.2 [klein] 4B

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Excellent primary title rendering with clean typography
  • + Coherent composition with strong vertical balance
  • + Great use of the fiery background elements including coals and embers
  • Failed to create an 'exploded' burger, showing a fully assembled one instead
  • Typographical error in 'ONLY' which is rendered as 'LNHLY'
  • Graphic style of the starburst feels flat compared to the rest of the image

FLUX.2 [klein] 4B

  • + Successfully rendered the price starburst with the requested fiery, glowing effect
  • + Higher realism in the food textures尤其是 the patty and bun
  • + Included all required text elements correctly with no spelling errors
  • Major typographical distortion in the main title rendering it illegible
  • Failed to depict an 'exploded' burger, showing an assembled double stack instead
  • The sparks look somewhat generic and repetitive

Verdict: Both models failed the primary compositional request for an 'exploded' view of the burger, opting instead for a whole burger suspended in air. FLUX.1 Kontext [dev] followed the layout better and produced a clearer background, but suffered from a spelling error, whereas FLUX.2 [klein] 4B had perfect spelling for the small text but completely failed the main brand title typography.

Chalkboard Menu

Text-to-Image

“Handwritten-style chalkboard menu in a cozy café, all text rendered in the exact same realistic chalk handwriting style with natural variations in letter size, slight slant, and chalk texture — no printed or digital fonts anywhere on the board. Title at the top in elegant cursive chalk handwriting: ‘TODAY’S SPECIALS – APRIL 30, 2026’. Below it, three menu items also in the same handwritten chalk style: ‘Truffle Mushroom Risotto – $24’, ‘Grilled Octopus with Lemon & Herbs – $28’, ‘Brown Butter Chocolate Chip Cookies – $9’. At the very bottom, smaller text in the identical handwritten chalk style (slightly smaller but still clearly legible with the same handwriting characteristics): ‘All items made fresh daily • Ask about our gluten-free options’. Warm ambient café lighting, visible chalk dust and smudges, realistic handwriting imperfections, no clean printed text anywhere.”

FLUX.1 Kontext [dev]
FLUX.2 [klein] 4B

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Excellent depiction of chalk texture and weight.
  • + Captures the 'cozy café' atmosphere with warm lighting.
  • + The handwriting style is very realistic and varied.
  • Significant spelling errors and word repetitions (e.g., 'Mashroom', 'with with', 'Octpus').
  • The date rendering is garbled and unreadable.

FLUX.2 [klein] 4B

  • + Successfully rendered the full date 'APRIL 30, 2026' correctly.
  • + The handwriting is consistent and legible across the entire board.
  • + Includes realistic chalk smudges and dust on the board surface.
  • Several spelling errors in the menu items (e.g., 'Truffel', 'Musheram', 'Ootrpous', 'Brawn').
  • The spacing in the title 'TODAY'S S PECIALS' is awkward.

Verdict: While both models struggle with spelling the specific menu items, FLUX.2 [klein] 4B followed the text prompt more accurately by correctly rendering the specific date requested. FLUX.1 Kontext [dev] has a more aesthetically pleasing chalk texture, but its failure to render the date and the repetitive word errors ('with with') make it a less successful adherence to the prompt.

The Reversed Rodeo

Text-to-Image

“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”

FLUX.1 Kontext [dev]
FLUX.2 [klein] 4B

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Excellent adherence to the 'horse on top' spatial instruction
  • + High quality facial details and skin textures
  • + Strong cinematic lighting and clean composition
  • The horse’s legs and anatomy are slightly distorted where they meet the astronaut's back
  • Floating orbs in the background appear a bit repetitive

FLUX.2 [klein] 4B

  • + Beautiful background with rich galactic colors and nebula details
  • + Good anatomical correctness of the horse
  • Failed the primary prompt instruction by placing the astronaut on top of the horse
  • The astronaut's face/eyes within the helmet are poorly rendered
  • Standard interpretation lacking the requested surrealism

Verdict: FLUX.1 Kontext [dev] is the clear winner as it successfully interpreted the surreal 'horse on top' instruction, whereas FLUX.2 [klein] 4B ignored the specific spatial constraint and produced a generic astronaut on a horse. FLUX.1 Kontext [dev] followed the logic of the prompt while maintaining higher overall visual fidelity in the face and suit details.

The Capybara Taxi Driver

Text-to-Image

“Photorealistic scene inside a yellow New York taxi at night. A capybara is driving, wearing a yellow taxi driver cap and a dark jacket. It has a calm, professional expression and both front paws on the steering wheel. In the back seat sits a human businesswoman in a coat, looking at her phone with a completely normal, bored expression (as if this is just another normal ride). Through the windows you can see the streets of Manhattan at night with blurred lights. Realistic taxi interior, photorealistic, detailed fur and fabric, 35mm lens, night lighting with reflections, shallow depth of field.”

FLUX.1 Kontext [dev]
FLUX.2 [klein] 4B

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Excellent photorealistic lighting and skin textures.
  • + Captures a very professional and calm capybara expression.
  • + Better integration of the clothing on the capybara's frame.
  • Only one paw is on the steering wheel instead of both front paws.
  • The businesswoman looks a bit too concerned/alert rather than bored.

FLUX.2 [klein] 4B

  • + Strict adherence to the 'both front paws on the steering wheel' instruction.
  • + The passenger perfectly captures the 'bored' and 'normal' expression.
  • + Composition clearly identifies the front and back seat separation.
  • The scale of the capybara relative to the steering wheel feels slightly off.
  • The capybara's texture is slightly more painterly than photorealistic.

Verdict: FLUX.2 [klein] 4B followed the prompt instructions more precisely, specifically capturing both paws on the steering wheel and the requested bored expression of the passenger. While FLUX.1 Kontext [dev] has superior lighting and technical photorealism, it failed to place both paws on the wheel and the passenger appears tense rather than nonchalant.

The Halloween Invitation

Text-to-Image

“Vintage gothic Halloween party invitation. Dark parchment poster, spooky border with webs and thorns, central glowing jack-o-lantern, bats, twisted trees, moody night sky. Add elegant gothic title text saying "Halloween Party Invitation", a small scroll banner saying "You are invited to a night of frights", and event details at the bottom: Date: 30.10.2026 Time: 7pm Location: The Arches, NYC Spooky but polished, cinematic lighting, square format.”

FLUX.1 Kontext [dev]
FLUX.2 [klein] 4B

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Excellent large-scale text legibility for the main title.
  • + Clean border layout following the thorn and web prompt.
  • Internal banner text is gibberish and poorly rendered.
  • Lacks a moody night sky and atmospheric background, feeling a bit flat.
  • Spelling errors in the location name and date format.

FLUX.2 [klein] 4B

  • + Beautiful atmospheric mood with twisted trees, foggy sky, and cinematic lighting.
  • + Includes the requested scroll banner with legible text.
  • + Border more accurately reflects the requested 'webs and thorns' combination.
  • The main title text has several spelling errors and character artifacts.
  • Minor spelling errors in the date and labels at the bottom.
  • Some fine detail artifacts in the cobweb textures.

Verdict: While FLUX.1 Kontext [dev] handles the largest text more clearly, FLUX.2 [klein] 4B is the far superior image in terms of atmosphere, composition, and prompt adherence. FLUX.2 [klein] 4B captures the 'cinematic lighting' and 'moody night sky' requested, whereas FLUX.1 Kontext [dev] provides a very basic black background with severe text corruption in the smaller scroll.

Bald man challenge

Image Editing
Edit instruction

“Give the person a full, thick head of natural hair with realistic texture, density, and a natural hairline. Preserve facial features and lighting.”

Before After
FLUX.1 Kontext [dev]
Before After
FLUX.2 [klein] 4B

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Successfully added thick hair that blends well with existing sideburns.
  • + Maintained the overall lighting and color palette of the image.
  • Failed to preserve facial features, significantly altering the man's eye shape, nose, and glasses.
  • The hair texture appears slightly overly groomed and digital compared to the original image's grit.

FLUX.2 [klein] 4B

  • + Excellent preservation of the original person's facial features and glasses.
  • + Realistic, messy hair texture that perfectly matches the established aesthetic of the beard and environment.
  • + Perfectly blended hairline and integration with the original head shape.
  • None notable; it followed all instructions and constraints perfectly.

Verdict: FLUX.2 [klein] 4B is the clear winner as it successfully added the hair while perfectly preserving the person's identity and the image's original quality. In contrast, FLUX.1 Kontext [dev] significantly altered the man's face and glasses, making it look like a different person entirely.

Isometric Miniature Diorama Scenes

Text-to-Image

“Create a clear, 45° top-down isometric miniature 3D cartoon scene of Japan's signature dish: sushi, with soft refined textures, realistic PBR materials, gentle lighting, on a small raised diorama base with minimal garnish and plate. Solid light blue background. At top-center: 'JAPAN' in large bold text, 'SUSHI' below it, small flag icon. Perfectly centered, ultra-clean, high-clarity, square format.”

FLUX.1 Kontext [dev]
FLUX.2 [klein] 4B

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Excellent typography rendering with bold, clear text.
  • + Perfectly captures the 'cartoon miniature' aesthetic with soft, clay-like textures.
  • + Very balanced and clean composition on a diorama base.
  • The flag icon is stylized and abstract rather than a clear Japanese flag.
  • The sushi design is oversimplified, looking more like a toy than a food item.

FLUX.2 [klein] 4B

  • + High-quality PBR materials with realistic subsurface scattering on the fish and rice.
  • + Captures the isometric 45° angle perfectly.
  • + Followed the request for a small plate and minimal garnish beautifully.
  • Typos in the text; it reads 'SUSH' followed by a flag icon instead of 'SUSHI'.
  • The flag icon resembles the flag of Austria or Latvia rather than Japan.
  • The layout is less centered vertically than requested.

Verdict: FLUX.1 Kontext [dev] followed the text instructions much better, producing 'JAPAN' and 'SUSHI' without errors, though the 'cartoon' styling is very heavy. FLUX.2 [klein] 4B produced a much more visually impressive and realistic 'miniature' with superior materials, but ultimately failed on the text rendering (missing the 'I' in Sushi) and the flag icon. FLUX.1 Kontext [dev] is the winner for total prompt adherence and graphic clarity.

Over-the-top cartoon caricature

Editing
Edit instruction

“Create a caricature of me and my job. Make it exaggerated and humorous, incorporating my profession as a tv show anchor and my love for dogs and hockey.”

Source
FLUX.1 Kontext [dev]
FLUX.2 [klein] 4B

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Maintains the subject's casual denim outfit from the source image.
  • + Captures a distinct pop-art caricature style.
  • + Includes a clear representation of a dog.
  • Fails to include any hockey elements.
  • The TV anchor component is represented by a small, basic computer monitor rather than a studio.
  • Text generation is messy and nonsensical.

FLUX.2 [klein] 4B

  • + Successfully incorporates the TV anchor desk/studio setting and multiple dogs.
  • + Excellent facial caricature that captures the essence of the subject with humorous exaggeration.
  • + Includes hockey motifs on the background screens.
  • Changes the subject's outfit from casual denim to a formal news suit, losing some source preservation.
  • The hockey integration is subtle within the background graphics rather than being a primary 'prop'.

Verdict: FLUX.2 [klein] 4B is the clear winner as it successfully integrates all requested themes including the job (TV anchor), dogs, and hockey (seen in the background graphics), while providing a much better 'caricature' facial style. FLUX.1 Kontext [dev] failed to include the hockey theme entirely and used a very literal and messy interpretation of the 'job' prompt.

Adorable Baby Animals in Sunny Meadow

Text-to-Image

“Hyper-photorealistic scene of fluffy baby animals—a golden retriever puppy, tabby kitten, baby bunny, and red fox kit—with big expressive eyes and ultra-detailed soft fur, playfully chasing butterflies and tumbling together in a lush wildflower meadow, warm golden sunrise light with god rays and dew sparkles, joyful wholesome vibe, 8K masterpiece.”

FLUX.1 Kontext [dev]
FLUX.2 [klein] 4B

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Energetic composition with dynamic poses including running and jumping.
  • + Beautiful golden hour lighting that feels warm and cohesive.
  • Failed to include the fox kit and baby bunny as requested in the prompt.
  • Anatomical oddity on the kitten's front right leg which appears to have too many toes.

FLUX.2 [klein] 4B

  • + Better adherence to the prompt by including the fox kit and multiple kittens.
  • + Excellent use of god rays and lighting to create a dreamlike, masterwork quality.
  • + Superior fur texture and detail on the animals' faces.
  • Failed to include the baby bunny.
  • The composition is a bit crowded with two kittens instead of the requested diverse mix.

Verdict: FLUX.2 [klein] 4B is the clear winner for its superior rendering of textures and much better adherence to the specific animals requested, including the fox kit which FLUX.1 Kontext [dev] completely omitted. While both models failed to include the baby bunny, FLUX.2 [klein] 4B captured the requested 'god rays' and 'ultra-detailed fur' with much higher fidelity.

Studio Ghibli Anime Style

Editing
Edit instruction

“Transform this photo into a Studio Ghibli–inspired illustration. Use soft pastel colors, hand-painted textures, gentle lighting, dreamy backgrounds, and a warm, nostalgic mood”

Source
FLUX.1 Kontext [dev]
FLUX.2 [klein] 4B

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Excellent preservation of the original pose and facial expressions.
  • + Clean line art and vibrant colors that mimic modern anime styles.
  • + High clarity and structural consistency with the source image.
  • Lacks the requested hand-painted, soft texture characteristic of Studio Ghibli.
  • The lighting is flat and digital rather than reflecting a 'dreamy' mood.

FLUX.2 [klein] 4B

  • + Perfectly captures the Studio Ghibli aesthetic with soft pastel colors and watercolor textures.
  • + Successfully transforms the background into a dreamy, hand-painted landscape while maintaining the original layout.
  • + Lighting feels nostalgic and gentle as requested.
  • Loss of the specific 'shocked' expression on the woman on the right.
  • The character features are slightly more generic compared to the original subjects' faces.

Verdict: FLUX.2 [klein] 4B is the clear winner for stylization, as it perfectly executed the 'Studio Ghibli' aesthetic with beautiful hand-painted textures and soft pastel tones. While FLUX.1 Kontext [dev] preserved the original facial expressions and details more accurately, it failed to achieve the specific artistic mood and texture requested in the prompt, resulting in a generic digital anime look.

Golden Hour Stroll

Image Editing
Edit instruction

“Add dynamic motion to this photo: make hair blow in the wind, add leaves flying, energetic and lively feel.”

Before After
FLUX.1 Kontext [dev]
Before After
FLUX.2 [klein] 4B

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Excellent preservation of the original woman's identity and facial features.
  • + Subtle and natural-looking wind effect in the hair.
  • + Maintains very high coherence with the source background and lighting.
  • The flying leaves are very sparse, with only about three tiny green specks visible.
  • Misses the 'energetic and lively' feel by being too conservative with the edits.

FLUX.2 [klein] 4B

  • + Stronger adherence to the 'flying leaves' instruction with a high density of leaves.
  • + Effective flow and movement in the hair.
  • + Adds a more noticeable sense of 'dynamic motion' as requested.
  • Slight alteration to the woman's facial features compared to the source image.
  • Some leaves appear flat or poorly integrated into the 3D space of the scene.

Verdict: FLUX.1 Kontext [dev] did an excellent job of preserving the source image but failed to meaningfully add flying leaves, including only a few small green artifacts. FLUX.2 [klein] 4B better captured the requested energetic atmosphere with many flying leaves and dynamic hair, although it slightly changed the subject's face in the process.

Vintage Cafe Logo

Text-to-Image

“Vintage minimalist restaurant logo for "Caffè Florian", retro cloche dome with steam and "Est. 1720" banner, classic typography, warm brown and cream tones, subtle texture on light background, vector emblem style.”

FLUX.1 Kontext [dev]
FLUX.2 [klein] 4B

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Perfect text rendering with correct spelling
  • + Clean and crisp vector-style lines
  • + Effective minimalist aesthetic
  • Missed the 'banner' element for the date
  • The cloche dome looks more like a building dome or a crown
  • Very little texture present

FLUX.2 [klein] 4B

  • + Included the banner and subtle paper texture requested
  • + The cloche dome is clearly recognizable as a food cover
  • + Classic typography fits the vintage theme well
  • Misspelled the name as 'FLAXTION'
  • Duplicated the foundation date
  • Graphic lines on the banner are slightly messy and inconsistent

Verdict: FLUX.1 Kontext [dev] produced a much cleaner and more professional-looking vector logo with perfect spelling, though it missed the requested banner element. FLUX.2 [klein] 4B captured more of the prompt's specific details like the texture and banner, but failed on the basic requirement of spelling the primary name correctly. FLUX.1 Kontext [dev] is the winner for its clarity and accuracy.

Apollo 11: Journey to Tranquility

Text-to-Image

“Create a clean, modern vector infographic poster about the Apollo 11 mission. NASA-inspired palette (navy, white, muted red, light gray). Flat-vector style, crisp lines, consistent iconography, subtle gradients only. Steps (stop at landing): 1. Launch (Saturn Vicon) 2. Earth Orbit (Earth + orbit ring icon) 3. Translunar (trajectory arc icon) 4. Lunar Orbit (Moon + orbit ring icon) 5. Descent (lunar module descending icon) 6. Landing (lunar module on the surface icon) Small supporting elements (minimal text): • Crew strip: three silhouette icons with only last names: Armstrong, Aldrin, Collins. • Landing site marker: Moon pin labeled "Tranquility" only. Layout constraints: generous margins, large readable labels, clean background with subtle stars. Vector-only, print-poster look, high resolution.”

FLUX.1 Kontext [dev]
FLUX.2 [klein] 4B

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Strong adherence to the requested color palette
  • + Good vector-style abstract icons
  • + Clearer typography on the main title
  • Extreme spelling errors and garbled text throughout the steps
  • Icons do not clearly represent the specific lunar mission steps requested
  • Messy layout with overlapping text and icons

FLUX.2 [klein] 4B

  • + Better overall composition and infographic layout
  • + Icons more closely represent the requested items like Earth, orbit, and the Lunar Module
  • + Successfully included specific names like 'Aldrin' and 'Collins'
  • Major typos in the main title ('APLLO 1UT 1J')
  • The Saturn V rocket design is structurally incorrect and looks like a generic missile
  • Included green in the color palette which was not requested

Verdict: While both models struggled with text rendering, FLUX.2 [klein] 4B is the winner because it actually attempted to follow the sequential logic of the infographic with recognizable icons for Earth and the landing module. FLUX.1 Kontext [dev] produced a more stylish graphic, but its icons were mostly abstract shapes and the supporting text was completely illegible gibberice.

Next steps

Explore each model